Apply Two-Stage Grey Incidence Analysis with Dynamic Weights to Improve the Quality of Default Prediction

應用二階段動態權重灰關聯分析提升違約預測之品質

10.6220/joq.2015.22(5).03

周宗南(Tsung-Nan Chou)

違約預測 ； 證據推理 ； 灰色關聯分析 ； 服務品質保證 ； default prediction ； evidential reasoning ； grey incidence analysis ； service quality assurance

品質學報

22卷5期（2015 / 10 / 31）

405 - 426

英文

由於台灣經濟衰退和失業率上升，除了對信用卡產業造成很大的負面影響外，也為信用卡發卡機構的違約品保分析師及管理經理帶來很大的壓力，迫使他們必須採取有效措施以防止不斷上升的違約率。本文應用灰色關聯分析建構一兩階段的信用卡違約預測模型，在第一階段的特徵選取中應用證據推理方法來結合不同灰色關聯分析所產生的變數排序，透過資料融合為一最佳排序來挑選重要變數。在第二階段的違約案例預測則採用動態權重的方式來校正並取代原有灰關聯度計算所使用的平均權重。實證結果顯示，在各項模型績效評估指標中以兩階段違約預測模型的準確度最高，其預測準確性可以顯著提升到89.7%。證據推理除了可以減少不同灰色關聯分析所產生的不一致結果，同時也可以提供一種有效的折衷解決方案進行特徵選取。此外利用訓練樣本的機率分佈來計算每一筆測試樣本進行樣式比對時所需的權重，可以有效地動態調整灰色關聯分析提升預測品質。此兩階段違約預測模型能夠協助金融機構違約品保分析師及管理經理改善與違約個案執行相關的品管與稽核流程。

Both the economic downturn and increasing unemployment rate in Taiwan have given rise to a number of negative impacts on the credit card industry and put pressure on the default managers and default quality assurance analyst within a financial institution to take effective measures against the rising default rate. This paper proposed a predictive model of two-stage grey incidence analysis (GIA) which applied evidential reasoning approach to combine various attribute rankings of GIAs in feature selection at the first stage, and then calibrated the instance predictions of GIA with dynamic weighting method for the classification of delinquency cases at the second stage. The experimental results indicated the predictive model performed better in most evaluation metrics and its accuracy could be significantly improved to 89.7%. The evidential reasoning provided an efficient compromise solution in feature selection. Moreover, the GIA model for optimal instance matching was effectively adapted by the dynamic weights calculated for testing samples based on the probability distribution of training samples. The two-stage predictive model will be able to assist default managers and analysts in performing quality control audits to the default related processes.

1. Banking Bureau, Financial Supervisory Commission, R.O.C., (August 2014), Statistics of credit card business operation, .
2. Fannie Mae Announcement, (October 2014), Lender quality control programs, plans, and processes,selling guide: D1-1-01, Federal National Mortgage Association SEL-2014-10, < https://www.fanniemae.com/>.
3. Frame, W. S., Gerardi, K., and Willen, P. S., 2013, Supervisory Stress Tests, Model Risk, and Model Disclosure: Lessons from OFHEO, Working Paper, Atlanta, GA.
4. Agarwal, S.,Liu, C.(2003).Determinants of credit card delinquency and bankruptcy:macroeconomic factors.Journal of Economics and Finance,27(1),75-84.
5. Banerjee, P.,Canals-Cerdá, J. J.(2012).,Philadelphia, PA.:Federal Reserve Bank of Philadelphia.
6. Bekkar, M.,Djemaa, H. K.,Alitouche, T. K.(2013).Evaluation measures for models assessment over imbalanced data sets.Journal of Information Engineering and Applications,3(10),27-38.
7. Chou, T. N.(2007).A novel prediction model for credit card risk management.Proceedings of The Second International Conference on Innovative Computing, Information and Control
8. Deng, J. L.(1989).Introduction to grey system theory.Journal of Grey System,1(1),1-24.
9. Deng, J. L.(1988).Grey Systems.Hong Kong:China Ocean Press.
10. Elliotta, G.,Lieli, R. P.(2010).Predicting binary outcomes.Journal of Econometrics,174,15-26.
11. Ertekin, S.,Huang, J.,Bottou, L.,Giles, L.(2007).Learnning on the border: active learning in imbalanced data classification.Proceedings of the 6th ACM Conference on Information and Knowledge Management
12. Gao, L.,Mock, T. J.,Srivastava, R. P(2011).An evidential reasoning approach to fraud risk assessment under Dempster-Shafer Theory: a general framework.Proceedings of 2011 the 44th International System Sciences (HICSS) Conference
13. Gross, D. B.,Souleles, N. S.(2002).An empirical analysis of personal bankruptcy and delinquency.Review of Financial Studies,15,319-347.
14. Higgins, J. P.,Thompson, S. G.,Deeks, J. J.,Altman, D. G.(2003).Measuring inconsistency in meta-analyses.British Medical Journal,327(7414),557-560.
15. Kaan, E.(2014).Risk management, quality control and statistics (part 1).Mortgage Compliance Magazine,7(1),10-14.
16. Kuncheva, L. I.(2014).Combining Pattern Classifiers: Methods and Algorithms.New York:John Wiley.
17. Maimon, O.(ed.),Rokach, L.(ed.)(2005).Data Mining and Knowledge Discovery Handbook.New York:Springer.
18. Raftery, A. E.,Tanner, M. A.,Wells, M. T.(2002).Statistics in the 21st Century.Boca Raton, FL.:Chapman and Hall/CRC Press.
19. Shafer, G.(1987).Probability judgement in artificial intelligence and expert systems.Statistical Science,2(1),3-16.
20. Shafer, G.(1976).A Mathematical Theory of Evidence.Princeton, NJ:Princeton University Press.
21. Sheskin, D. J.(2004).Handbook of Parametric and Nonparametric Statistical Procedures.London:Chapman& Hall.
22. Stein, R. M.(2007).Benchmarking default prediction models: pitfalls and remedies in model validation.Journal of Risk Model Validation,1(1),77-113.
23. Subashini, T. S.,Ramalingam, V.,Palanivel, S.(2009).Breast mass classification based on cytological patterns using RBFNN and SVM.Expert Systems with Applications,36(3),5284-5290.
24. Wang, S.,Yao, X.(2012).Multiclass imbalance problems: analysis and potential solutions.IEEE Transactions on Systems, Man, and Cybernetics Part B: Cybernetics,42(4),1119-1130.
25. Wen, K. L.(2004).Grey Systems: Modeling and Prediction.Tucson, AZ:Yang's Scientific Press.
26. Wu, H.,Siegel, M.,Stiefelhagen, R.,Yang, J.(2002).Sensor fusion using Dempster-Shafer Theory.Proceedings of IEEE Instrumentation and Measurement Technology Conference
27. Yamaguchi, D.,Li, G.-D.,Nagai, M.(2006).Evaluation on the effectiveness of grey relational analysis models.Proceedings of 11th Grey System Theory and Application Conference